win10系统配置GPU版本Pytorch的详细教程

import pycuda.driver as drv
import pycuda.tools,pycuda.autoinit,numpy
import numpy.linalg as la
from pycuda.compiler import SourceModule
 
mod = SourceModule("""
__global__ void multiply_them(float *dest, float *a, float *b)
{
  const int i = threadIdx.x;
  dest[i] = a[i] * b[i];
}
""")
 
multiply_them = mod.get_function("multiply_them")
 
a = numpy.random.randn(400).astype(numpy.float32)
b = numpy.random.randn(400).astype(numpy.float32)
 
dest = numpy.zeros_like(a)
multiply_them(drv.Out(dest), drv.In(a), drv.In(b),block=(400,1,1))
 
print(dest-a*b)